fix: fix quant linear autotune

server/text_generation_server/utils/gptq/custom_autotune.py

@@ -88,7 +88,7 @@ class Autotuner(triton.KernelInterface):
             # In testings using only 40 reps seems to be close enough and it appears to be what PyTorch uses
             # PyTorch also sets fast_flush to True, but I didn't see any speedup so I'll leave the default
             return triton.testing.do_bench(
-                kernel_call, percentiles=(0.5, 0.2, 0.8), rep=40
+                kernel_call, quantiles=(0.5, 0.2, 0.8), rep=40
             )
         except triton.OutOfResources:
             return (float("inf"), float("inf"), float("inf"))